Search

The Lower Paleozoic reservoir in the Micangshan tectonic belt is a new shale gas exploration area with excellent potential. However, the black shale's sedimentary environment and tectonic setting and their effects on pore-scale fluid flow have not been thoroughly elucidated and urgently require further research. A large amount of trace and rare earth element data of black shale in this area was tested to analyze the sediment's provenance, tectonic setting, and coupling process, and nuclear magnetic resonance was applied for fluid flow ability determination. The characteristics of trace elements and rare earth elements in shale samples were drilled from the Upper Sinian Doushantuo Formation, the Lower Cambrian Niutitang Formation, and the Lower Silurian Longmaxi Formation in the Micangshan tectonic belt. The results reveal that the provenance of the shales was dominated by island arc volcanic rocks and some ancient fine-grained sediments. The provenances of shale in the Micangshan, Huijunba, and Zhenba areas may have a strong genetic relationship with the igneous rocks from the nearest Hannan massif. The provenance of the Niutitang shale in the Ningqiang area may comprise sediments derived from the Longmenshan continental rift system. The provenance of the shale tends to transition from the island arc to the continental margin from the depositional stage of the Doushantuo Formation to the Longmaxi Formation. The Micangshan tectonic belt inherited the tectonic evolution of the South China block, North China block, and Qinling, and those blocks provided the igneous provenance of the shale by island arcs, which were formed due to weathering caused by the process of subduction and collision orogeny. The movable fluid distribution of the Longmaxi Formation and Niutitang Formation is relatively uniform, and excessive pursuit of large amount of movable fluid will be counterproductive to the shale reservoir. The proportion of the cracks was generally less than 3% except for one sample from the Doushantuo Formation with 12.06%. Based on the centrifugation force in this research, the low fluid flow limits were less than 1.47, and there are strong positive relationships between movable fluid saturation and saturated porosity. In this study, the coupling relationship between the material source and pore scale flow is discussed for the first time, and the results can provide theoretical references for local provenance analysis and tectonic movement. [ABSTRACT FROM AUTHOR]

Anomaly detection in time series has attracted much attention recently and is quite a challenging task. In this paper, a novel deep-learning approach (AL-CNN) that classifies the time series as normal or abnormal with less domain knowledge is proposed. The proposed algorithm combines Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) to effectively model the spatial and temporal information contained in time-series data, the techniques of Squeeze-and-Excitation are applied to implement the feature recalibration. However, the difficulty of selecting multiple parameters and the long training time of a single model make AL-CNN less effective. To alleviate these challenges, a hybrid dynamic membrane system (HM-AL-CNN) is designed which is a new distributed and parallel computing model. We have performed a detailed evaluation of this proposed approach on three well-known benchmarks including the Yahoo S5 datasets. Experiments show that the proposed method possessed a robust and superior performance than the state-of-the-art methods and improved the average on three used indicators significantly. [ABSTRACT FROM AUTHOR]